https://livekit.io logo
Join Slack
Powered by
5-12-23 14:44:04,192 - livekit.agents - ERROR - Er...
# ask-ai
r
2025-12-23 144404,192 - livekit.agents - ERROR - Error in _realtime_reply_task Traceback (most recent call last): File "/usr/local/lib/python3.12/site-packages/livekit/agents/utils/log.py", line 16, in async_fn_logs return await fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/livekit/agents/voice/agent_activity.py", line 2185, in _realtime_reply_task generation_ev = await self._rt_session.generate_reply( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ livekit.agents.llm.realtime.RealtimeError: generate_reply timed out waiting for generation_created event. 2025-12-23 144404,194 - __mp_main__ - INFO - ✅ Transfer message completed, shutting down session 2025-12-23 144404,195 - __mp_main__ - INFO - ✅ Session shutdown initiated 2025-12-23 144404,192 - livekit.agents - ERROR - Error in _realtime_reply_task Traceback (most recent call last): File "/usr/local/lib/python3.12/site-packages/livekit/agents/utils/log.py", line 16, in async_fn_logs return await fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/livekit/agents/voice/agent_activity.py", line 2185, in _realtime_reply_task generation_ev = await self._rt_session.generate_reply( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ livekit.agents.llm.realtime.RealtimeError: generate_reply timed out waiting for generation_created event. Traceback (most recent call last): File "/usr/local/lib/python3.12/site-packages/livekit/agents/utils/log.py", line 16, in async_fn_logs return await fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/livekit/agents/voice/agent_activity.py", line 2185, in _realtime_reply_task generation_ev = await self._rt_session.generate_reply( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ livekit.agents.llm.realtime.RealtimeError: generate_reply timed out waiting for generation_created event. {"message": "Error in _realtime_reply_task\nTraceback (most recent call last):\n File \"/usr/local/lib/python3.12/site-packages/livekit/agents/utils/log.py\", line 16, in async_fn_logs\n return await fn(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.12/site-packages/livekit/agents/voice/agent_activity.py\", line 2185, in _realtime_reply_task\n generation_ev = await self._rt_session.generate_reply(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\nlivekit.agents.llm.realtime.RealtimeError: generate_reply timed out waiting for generation_created event.", "level": "ERROR", "name": "livekit.agents", "exc_info": "Traceback (most recent call last):\n File \"/usr/local/lib/python3.12/site-packages/livekit/agents/utils/log.py\", line 16, in async_fn_logs\n return await fn(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.12/site-packages/livekit/agents/voice/agent_activity.py\", line 2185, in _realtime_reply_task\n generation_ev = await self._rt_session.generate_reply(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\nlivekit.agents.llm.realtime.RealtimeError: generate_reply timed out waiting for generation_created event.", "pid": 634, "job_id": "AJ_wWX2TsACGRm2", "room_id": "RM_Uzb8CZF2nZXr", "timestamp": "2025-12-23T091404.192517+00:00"}
t
Thanks for reaching out, Gaurav. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.
Thanks — I can help troubleshoot the repeated “generate_reply timed out waiting for generation_created event” errors you’re seeing. I’m responding to the error traces you pasted from 
agent_activity.py
where 
self._rt_session.generate_reply(...)
timed out. To narrow this down quickly, could you provide the following details? 1. Which realtime LLM provider and model are you using (e.g., OpenAI Realtime, Gemini Live)? 2. Are you running agents on burstable cloud instances (t3/t4) or fixed-performance instances (m5/c5/etc.)? 3. Do you see any network interruptions or WebSocket disconnects in your logs around the same timestamps? 4. Have you recently changed realtime-related config (turn_detection, modalities, timeouts, or provider key) or upgraded the 
livekit-agents
package? 5. Can you enable and share a short snippet of RealtimeSession event logs (events like 
generation_created
, 
input_speech_started
, 
error
) around a failing request? Immediate steps you can take while I wait for the above: • Verify provider connectivity and API key validity by calling the provider’s realtime test endpoint outside LiveKit. • If on AWS t3/t4, switch to a fixed-performance instance or monitor CPU credits to rule out throttling. • Add logging for RealtimeSession events to confirm whether 
generation_created
is emitted or the session disconnects before it:
Copy code
session._rt_session.on("generation_created", lambda ev: print("generation_created", ev))
  session._rt_session.on("error", lambda e: print("realtime error", e))
  session._rt_session.on("disconnect", lambda: print("realtime disconnected"))
• Implement simple retry-with-backoff around 
generate_reply
to handle transient provider delays. If you share the answers to (1–5) and a short sample of the event logs, I’ll recommend targeted fixes (config changes, recommended instance types, or code snippets) specific to your setup. Sources: Agents Framework | livekit/livekit_composite | DeepWiki | Troubleshooting Latency and Timeout Errors with Turn Detection on AWS | examples/voice_agents | livekit/livekit_composite | DeepWiki | Voice AI quickstart | LiveKit docs
15 Views
Open in Slack
PreviousNext
Powered by